Alan Agresti Distinguished Professor Emeritus Department of Statistics University of Florida 204 Griffin-Floyd Hall Gainesville, FL 32611-8545 PHONE: (352) 273-2981 FAX: (352) 392-5175 E-MAIL: aa "at" stat "dot" ufl "dot" edu I will not be working for UF again until January, 2009. Until then, I am not checking e-mail regularly, and I'm sorry but I am unable to referee papers and grant proposals, prepare promotion reviews, give consulting advice about statistics and statistical software, etc.

Honors

• Honorary doctorate, De Montfort University (Leicester, U.K.), 1999
• Statistician of the Year, Chicago chapter of American Statistical Association, 2003
• Recipient of the first Herman Callaert Leadership Award in Statistical Education and Dissemination, Limburgs Universitaire, Diepenbeek, Belgium, 2004
• Fellow, American Statistical Association, 1990
• 36th Annual Allen T. Craig lecturer, University of Iowa, 2006
• University of Florida Research Foundation (UFRF) Professorship, 1997-2000
• University of Florida Distinguished Professor, 2000-
• College Award for Excellence in Teaching (TIP), 1995
• Excellence in Continuing Education Award from American Statistical Association, 2002
• Keynote lectures at conferences include Swiss Statistical Society (1992), French Biometric Society (1992), Conference on Statistical Issues in Biopharmaceutical Environments (1999) in the UK, Army Conference on Applied Statistics (2002), CDC annual awards meeting (2003), Applied Statistics in Ireland (2004), Hawaii International Conference on Statistics, Mathematics, and Related Fields (2004), International Society of Clinical Biostatistics (2005) in Hungary, CompStat (2006) in Italy, Applied Statistics (2007) in Slovenia, and invited lectures and short courses in about 30 countries

Research Interests

My primary research interests are in categorical data analysis. Research topics in recent years include small-sample confidence intervals for binomial proportions and odds ratios, and models for repeated categorical responses. My other areas of interest include generalized linear models, longitudinal data analysis, social statistics, biostatistics, and statistical education (particularly service courses and the presentation of statistical ideas to nonstatisticians).

Textbook Information and Supplemental Files

1. The text
Statistics: The Art and Science of Learning from Data (2nd edition, Pearson Prentice Hall, 2008) was written with Christine Franklin of the Statistics Department at the University of Georgia. This text is designed for a one-term or two-term undergraduate course or a high school AP course on an introduction to statistics, presented with a conceptual approach. The text includes numerous activities and links to applets to aid in student learning (although use of these by the instructor is optional). The link above has a Table of Contents and other information about the book. Many supplemental materials are available from Pearson Prentice Hall, including an annotated instructor's edition, a lab workbook, videotaped lectures, and software supplements. Contact Ms. Dierdre Lynch, the Editor-in-Chief for Statistics and Mathematics at Pearson Education, for details (Deirdre.Lynch@AWL.com).

2. The text
Statistical Methods for the Social Sciences (4th edition, Pearson Prentice Hall, 2008) is designed for a two-semester sequence. The new edition of this text has just been published. The book begins with the basics of statistical description and inference, and the second half concentrates on regression methods, including multiple regression, ANOVA and repeated measures ANOVA, analysis of covariance, logistic regression, and generalized linear models. For applets used in some exercises of the new edition, go to applets for SMSS. For a file containing many of the large data sets from the text, click on Website for SMSS. For examples of the use of the software Stata for various analyses for examples in this text, see the useful site set up by the UCLA Statistical Computing Center.

3. The text
Categorical Data Analysis, 2nd Edition

is in its second edition (Wiley, 2002). I've constructed a Website for Categorical Data Analysis that provides datasets used for examples, solutions to some odd-numbered exercises, information about software, and a list of some typos and errors. Dr. Laura Thompson has prepared a detailed manual (over 250 pages long!) on the use of R or S-Plus to conduct all the analyses in this text. You can get a copy of this excellent resource at Laura Thompson R and S manual for CDA. Compared with the first edition, this edition has more emphasis on logistic regression and generalized linear models. There are new chapters on an introduction to distributions and inference for discrete distributions, marginal models (ML and GEE), generalized linear mixed models (including random effects), and other mixture models (such as latent class models, the beta binomial, and nonparametric approaches). For more information about the new edition, see the Table of Contents at the link to Wiley's website at the image above of the book.

4. The text
An Introduction to Categorical Data Analysis

was recently published in a second edition (Wiley, 2007). It presents a nontechnical introduction to topics such as logistic regression. Compared with the first edition, this edition has more emphasis on logistic regression and generalized linear models. There are new chapters on an introduction to inference for discrete distributions, marginal models for clustered, correlated responses, and generalized linear mixed models (including random effects). This book is a lower-technical-level and shorter version of the "Categorical Data Analysis" text mentioned in (3) above. I've constructed a website for that text that provides information about the use of Software for Categorical Data Analysis such as SAS, R and S-Plus, SPSS, Stata, and StatXact. For SAS files containing data sets from the text, click on Website for Intro CDA. Here are some corrections for the 1st edition and a pdf file of corrections for the 2nd edition.

5. The text
Analysis of Ordinal Categorical Data

(Wiley, 1984) is also still available, but it's old, expensive, and needs revision. I am in the process of preparing a second edition for Wiley, hoping to publish it by 2009.

Some Publications (since 1997)

• Statistics: The Art and Science of Learning from Data, 2nd edition, Pearson Prentice Hall (2008), with Chris Franklin.
• An Introduction to Categorical Data Analysis, 2nd ed., Wiley (2007).
• Categorical Data Analysis, 2nd edition, Wiley (2002).
• Statistical Methods for the Social Sciences, 4th edition, Pearson Prentice Hall (2008) (with B. Finlay).
• A model for repeated measurements of a multivariate binary response, Journal of the American Statistical Association (1997).
• Evaluating agreement and disagreement among movie reviewers, CHANCE (1997) (with L. Winner).
• Approximate is better than exact for interval estimation of binomial proportions, The American Statistician (1998) (with B. Coull).
• Order-restricted inference for monotone trend alternatives in contingency tables Computational Statistics & Data Analysis (1998) (with B. Coull).
• On logit confidence intervals for the odds ratio with small samples, Biometrics (1999).
• The use of mixed logit models to reflect subject heterogeneity in capture-recapture studies, Biometrics (1999) (B. Coull and A. Agresti).
• Modeling a categorical variable allowing arbitrarily many category choices, Biometrics (1999) (with I. Liu).
• Modelling ordered categorical data: Recent advances and future challenges, Statistics in Medicine (1999).
• Random effects modeling of multiple binary responses using the multivariate binomial logit-normal distribution, Biometrics (2000) (B. A. Coull and A. Agresti).
• Strategies for comparing treatments on a binary response with multi-center data, Statistics in Medicine (2000) (with J. Hartzel).
• Hierarchical Bayesian analysis of binary matched pairs data, Statistica Sinica (2000) (M. Ghosh, M. Chen, A. Ghosh, and A. Agresti).
• Noninformative priors for one parameter item response models, Journal of Statistical Planning and Inference (2000) (M. Ghosh, M. Chen, A. Ghosh, and A. Agresti)
• Challenges for categorical data analysis in the twenty-first century, in Statistics for the 21st Century, edited by C. R. Rao and G. J. Szekely, Marcel Dekker (2000)
• Summarizing the predictive power of a generalized linear model, Statistics in Medicine (2000) (B. Zheng and A. Agresti)
• Simple and effective confidence intervals for proportions and difference of proportions result from adding two successes and two failures, The American Statistician (2000) (with B. Caffo)
• Random effects modeling of categorical response data, Sociological Methodology (2000) (A. Agresti, J. Booth, J. P. Hobert, and B. Caffo)
• Describing heterogeneous effects in stratified ordinal contingency tables, with application to multi-center clinical trials, Computational Statistics & Data Analysis (2001) (J. Hartzel, I. Liu, and A. Agresti)
• Strategies for modeling a categorical variable allowing multiple category choices, Sociological Methods and Research (2001) (A. Agresti and I. Liu)
• Exact inference for categorical data: recent advances and continuing controversies, Statistics in Medicine (2001)
• A correlated probit model for multivariate repeated measures of mixtures of binary and continuous responses, Journal of American Statistical Association (2001) (R.V. Gueorguieva and A. Agresti)
• On small-sample confidence intervals for parameters in discrete distributions, Biometrics (2001) (A. Agresti and Y. Min)
• Multinomial logit random effects models, Statistical Modelling (2001) (J. Hartzel, A. Agresti, and B. Caffo)
• Modeling clustered ordered categorical data: A survey, International Statistical Review (2001) (A. Agresti and R. Natarajan)
• Statistical issues in the 2000 U.S. Presidential election in Florida, Journal of Law and Public Policy (Fall 2001 issue) (A. Agresti and B. Presnell)
• The analysis of contingency tables under inequality constraints, Journal of Statistical Planning and Inference (2002) (A. Agresti and B. A. Coull).
• Measures of relative model fit, Computational Statistics and Data Analysis (2002) (A. Agresti and B. Caffo).
• Unconditional small-sample confidence intervals for the odds ratio, Biostatistics (2002) (A. Agresti and Y. Min).
• Modeling nonnegative data with clumping at zero: A survey, Journal of the Iranian Statistical Society (2002) (Y. Min and A. Agresti).
• Links between binary and multi-category logit item response models and quasi-symmetric loglinear models, for special issue of Annales de la Faculte des Sciences de Toulouse Mathematiques, to honor retirement of Henri Caussinus, (2002).
• Dealing with discreteness: Making `exact' confidence intervals for proportions, differences of proportions, and odds ratios more exact, Statistical Methods in Medical Research (2003)
• A class of generalized log-linear models with random effects, Statistical Modelling (2003) (B. A. Coull and A. Agresti).
• Effects and noneffects of paired identical observations in comparing proportions with binary matched-pairs data, Statistics in Medicine (2004) (A. Agresti and Y. Min).
• Improved confidence intervals for comparing matched proportions, Statistics in Medicine (2004) (A. Agresti and Y. Min).
• Interview with Alan Agresti, conducted by Jackie Dietz, STATS (The Magazine for Students of Statistics) (2004).
• Examples in which misspecification of a random effects distribution reduces efficiency, Computational Statistics & Data Analysis (2004) (A. Agresti, P. Ohman, and B. Caffo).
• The analysis of ordered categorical data: An overview and a survey of recent developments, invited discussion paper for the Spanish Statistical Journal, TEST (2005) (I. Liu and A. Agresti).
• Multivariate tests comparing binomial probabilities, with application to safety studies for drugs, Applied Statistics (JRSS-C) (2005) (A. Agresti and B. Klingenberg).
• Frequentist performance of Bayesian confidence intervals for comparing proportions in 2x2 contingency tables, Biometrics (2005) (A. Agresti and Y. Min).
• Random effect models for repeated measures of zero-inflated count data, Statistical Modelling (2005) (Y. Min and A. Agresti).
• Bayesian inference for categorical data analysis, Statistical Methods and Application (Journal of the Italian Statistical Society), (2005) (A. Agresti and D. Hitchcock).
• Randomized confidence intervals and the mid-P approach, discussion of article by C. Geyer and G. Meeden, Statistical Science, (2005) (A. Agresti and A. Gottard).
• Multivariate extensions of McNemar's test, Biometrics, (2006) (B. Klingenberg and A. Agresti).
• Independence in multi-way contingency tables: S. N. Roy's breakthroughs and later developments, Journal of Statistical Planning and Inference, (2007) (A. Agresti and A. Gottard).
• A class of ordinal quasi-symmetry models for square contingency tables, Statistics and Probability Letters, (2007) (M. Kateri and A. Agresti).
• Nonconservative exact small-sample inference for discrete data, Computational Statistics and Data Analysis, (2007) (A. Agresti and A. Gottard).
• Modeling and inference for an ordinal effect size measure, Statistics in Medicine, to appear (2008) (E. Ryu and A. Agresti).
• Simultaneous confidence intervals for comparing binomial parameters, Biometrics, to appear (2008) (A. Agresti, M. Bini, B. Bertaccini, and E. Ryu).
• Pseudo-score inference for parameters in discrete statistical models, (A. Agresti and E. Ryu), UF Dept. of Statistics Technical Report.

Home pages for courses at UF

• STA 6127

• STA 6126

• STA 4504-5503

• STA 6505

• STA 7249

Other Information

The University of Florida Statistics Department home page

• UF STATISTICS

Jacki and Alan's

• Pound-wise guide to London from December--January 2007 issue of Gainesville magazine.

(Above home page picture among the bluebells taken by Jacki Levine in the Forest of Dean, Gloucestershire, England, my mother's home region)